Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    methods and techniques

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	de
    -0.07
    Escape
    -0.07
    üne
    -0.07
    汽车
    -0.06
     الذه
    -0.06
     honeymoon
    -0.06
    yal
    -0.06
     dx
    -0.06
    　　
    -0.06
    -Regular
    -0.06
    POSITIVE LOGITS
     büny
    0.06
    /*================================================================
    0.06
     redistribute
    0.06
     

↵
    0.06
     Irene
    0.06
     Germany
    0.06
     Asia
    0.06
    .department
    0.06
     identities
    0.06
    NUMBER
    0.06
    Act Density 0.060%

    No Known Activations